LLM Sandbox
io.github.vndee/llm-sandbox
Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
Description as published in the official MCP registry.
What we measured
| Endpoint | None listed (runs locally) | registry |
|---|---|---|
| GitHub stars | 1,128 | github.com/vndee/llm-sandbox |
| Last push | 2026-10-03 | GitHub API |
| Licence | MIT | GitHub API |
| Registry version | 0.3.43 · active · updated 2026-08-03 | registry |
| Package | pypi: llm-sandbox | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.
Related servers
- FetchSandbox A deterministic verification engine for agents. Proves a fix: fails on the old code…
- Kenwea — Sandbox Attestation & Agent Marketplace Signed sandbox verdicts on any artifact, plus an agent marketplace. No key, no signup, no…
- Sandboxd Code Run Hosted one-shot code execution: send a snippet plus optional files, get stdout, stderr…
- Shoon A2A Trust Services (pilot) Five trust services for agents: claim checks, citation audits, extraction, tripwires, work…
- SandboxAPI Execute code in 8 languages (Python, JS, TS, Go, Java, C++, C, Bash) in gVisor sandboxes.
- Ephemora Cell MCP — WASM Sandbox WASM sandbox for MCP tools. WASI-isolated, fuel/memory/I/O capped, attested.
Badge for your README
Shows the result of our latest check and links back to this page.
[](https://openforallofus.com/tools/io.github.vndee/llm-sandbox)Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name io.github.vndee/llm-sandbox.